CanopiiCanopiiAll serversEnterprise →
io.github.CSOAI-ORG/csoai

io.github.CSOAI-ORG/csoai v0.1.2

Security Trust Score
Grade F · Serious issues
Tier 1 · Public sourceHigh confidence · 92%
Declared MCP capabilities
ResourcesPrompts

This server scored F. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

2 issues capping this score
  • criticalNo command-injection sinks — 1 occurrence
  • mediumNo over-broad / destructive tools — 1 over-broad tool(s)
Reputation0stars0forks7open issuestodaylast commit<1yage

Security controls

Deterministic, evidence-backed. Score earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • Fail
    User-in-the-Loop / Approval Scopeguard1 over-broad tool(s)

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval. How many servers fail this?

    System Status

    Fix: Scope tools narrowly; avoid arbitrary command execution and destructive defaults.

  • Warn
    Strict JSON Schema Enforcementschemas not strict

    Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.

    Fix: Set additionalProperties:false and require explicit parameters on every tool.

  • Pass
    Indirect Prompt Injection (IPI) Defensesguardno injection markers

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

  • N/A
    Tool Definition Integrityguardno prior version to diff

    Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

  • Fail
    No command-injection sinksguard1 occurrence

    Untrusted tool input reaching a shell yields remote code execution. How many servers fail this?

    arena/functions/api/battle.ts:21

    Fix: Never pass tool arguments to a shell; use argv arrays with shell disabled.

  • Warn
    No path traversalguard13 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    _quarantine/public-legacy/deploy.js:14api-server/auth.js:85client/src/App.tsx:466client/src/components/EnforcementBanner.tsx:18

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    No SSRF sinksguard33 occurrences

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

    _quarantine/public-legacy/deploy.js:40api-server/a2a.js:93api-server/payments.js:96api-server/server.js:106

    Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.

  • Warn
    No known-vulnerable dependencies1 of 73 runtime deps vulnerable; worst low

    Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.

    [email protected] — GHSA-v422-hmwv-36x6

    Fix: Upgrade the flagged dependencies past their fixed versions.

  • Warn
    Established maintainerrecently published

    Brand-new / single anonymous maintainers raise takeover and malware risk.

    Fix: Publish under an established account/org; add multiple maintainers.

  • Warn
    Has a security policyno security policy

    A SECURITY.md gives a private path to report vulnerabilities.

    Fix: Add SECURITY.md with a disclosure contact and process.

  • Warn
    Adoption & popularitylimited adoption

    A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.

    Fix: Adoption grows naturally with real-world use; this never gates the score.

  • Pass
    No dynamic code executionguardno sinks found

    eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.

  • Pass
    No unsafe deserializationguardno sinks found

    pickle/yaml.load/etc. on untrusted data can execute code.

  • Pass
    No committed secretsguardno secrets found

    Hardcoded keys/tokens in published source are live credentials an attacker can use.

  • Pass
    Credentials sourced from environmentreads credentials from environment

    Reading secrets from env/secret stores avoids hardcoding them.

  • Pass
    Dependencies pinned (lockfile)lockfile present

    A lockfile makes installs reproducible and resistant to silent dependency swaps.

  • Pass
    Package name not typosquattingguarddistinct package name

    Names mimicking popular packages are a common malware delivery vector.

  • Pass
    Actively maintainedrecent commits

    Unmaintained servers don't receive security fixes.

  • Pass
    Repository not archivedguardactive

    Archived repositories will never be patched.

  • Pass
    Declares a licenseMIT

    A clear license is required for legal enterprise use.

  • Not checked
    No install/post-install scriptsguardnot determinable from PyPI metadata

    install hooks run arbitrary code on every consumer at install time.

  • Not checked
    Published with provenancenot determinable

    Build provenance attests the artifact was built from the claimed source by CI.

  • Not checked
    Signed releasesnot evaluated

    Signed releases let consumers verify artifacts weren't tampered with.

Transport & Trust Model

  • Pass
    Execution Sandboxingcontainerized

    A container/sandbox image limits blast radius; a server that runs natively has full host access.

  • Pass
    Network Exposureno bind-all detected

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

  • N/A
    Transport Encryption (TLS)guardno remote endpoints

    Plaintext HTTP exposes traffic and bearer tokens to interception.

  • N/A
    IAM / Authentication Scopingno remote endpoints

    OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

  • N/A
    Live Endpoint Reachablenot dynamically scanned

    A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.

  • N/A
    Authentication Enforced (live)not dynamically scanned

    If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Tools (80)

GPAIIEEEOECDLedgerOpenAIUNESCOExploreISO/IECMeta AIUK DSITUS NISTBaidu AIKAIST AIAnthropicChina CACEU AI ActMIT CSAILProvBenchSOAI-PDCACouncil OSJapan METIOxford FHIStart freeBrazil ANPDCanada AIDAChina TC260India MeitYMila QuebecNIST AI RMFHow It WorksStanford HAIAustralia DTABerkeley CHAICouncil SpaceG7 AI ProcessIBM AI EthicsISO/IEC 42001Microsoft RAISystem StatusUAE AI OfficeArticle 50 KitCambridge CSERSingapore IMDACyber self-scanGoogle DeepMindTry the CouncilAI Act BenchmarkEvidence PackageGovernance GraphIEEE 7000 SeriesMeasured ResultsReal-World GlobeSouth Korea MSITPartnership on AIPlans and PricingFree AI assessmentEuropean CommissionFramework crosswalkThe GSPC InstrumentThe Regulator AtlasThe Sovereign GlobeUN AI Advisory BodyArticle 50 ExplainedLive Ledger (signed)World Economic ForumAlan Turing InstituteArticle 50 CalculatorETH Zürich AI CenterNVIDIA Trustworthy AIThe Refutation LedgerTsinghua AI InstituteWhy CSOAI vs the restOffline Ed25519 VerifyOpen the full launcherUK AI Safety FrameworkUS AI Safety InstituteAI governance: the guideGlobal regulation trackerSingapore Model FrameworkYour Sovereign Twin (Design)